-
公开(公告)号：US20230326159A1
公开(公告)日：2023-10-12
申请号：US18149609
申请日：2023-01-03
Applicant: AUTODESK, INC.
Inventor： Hooman SHAYANI , Marco FUMERO , Aditya SANGHI
IPC: G06T19/20 , G06T17/00 , G06N3/08 , G06N3/0455
CPC classification number: G06T19/20 , G06T17/00 , G06N3/08 , G06N3/0455 , G06T2219/2024 , G06T2210/56 , G06T2219/2021
Abstract: One embodiment of the present invention sets forth a technique for performing style transfer. The technique includes determining a distribution associated with a plurality of style codes for a plurality of three-dimensional (3D) shapes, where each style code included in the plurality of style codes represents a difference between a first 3D shape and a second 3D shape, and where the second 3D shape is generated by applying one or more augmentations to the first 3D shape. The technique also includes sampling from the distribution to generate an additional style code and executing a trained machine learning model based on the additional style code to generate an output 3D shape having style-based attributes associated with the additional style code and content-based attributes associated with an object. The technique further includes generating a 3D model of the object based on the output 3D shape.
-
公开(公告)号：US20220156416A1
公开(公告)日：2022-05-19
申请号：US17523746
申请日：2021-11-10
Applicant: AUTODESK, INC.
Inventor： Peter MELTZER , Amir Hosein KHAS AHMADI , Pradeep Kumar JAYARAMAN , Joseph George LAMBOURNE , Aditya SANGHI , Hooman SHAYANI
IPC: G06F30/10
Abstract: In various embodiments, a style comparison application compares geometric styles of different three dimensional (3D) computer-aided design (CAD) objects. In operation, the style comparison application executes a trained neural network one or more times to map 3D CAD objects to feature map sets. The style comparison application computes a first set of style signals based on a first feature set included in the feature map sets. The style comparison application computes a second set of style signals based on a second feature set included in the feature map sets. Based on the first set of style signals and the second set of style signals, the style comparison application determines a value for a style comparison metric. The value for the style comparison metric quantifies a similarity or a dissimilarity in geometric style between a first 3D CAD object and a second 3D CAD object.
-
公开(公告)号：US20200051333A1
公开(公告)日：2020-02-13
申请号：US16536241
申请日：2019-08-08
Applicant: AUTODESK, INC.
Inventor： Hooman SHAYANI , Mark Thomas DAVIS , Andriy BANADYGA , Stephen BARLEY
Abstract: In various embodiments, a stylization subsystem automatically modifies a three-dimensional (3D) object design. In operation, the stylization subsystem generates a simplified quad mesh based on an input triangle mesh that represents the 3D object design, a preferred orientation associated with at least a portion of the input triangle mesh, and mesh complexity constraint(s). The stylization subsystem then converts the simplified quad mesh to a simplified T-spline. Subsequently, the stylization subsystem creases one or more of edges included in the simplified T-spline to generate a stylized T-spline. Notably, the stylized T-spline represents a stylized design that is more convergent with the preferred orientation(s) than the 3D object design. Advantageously, relative to prior art approaches, the stylization subsystem can more efficiently modify the 3D object design to improve overall aesthetics and manufacturability.
-
4.发明公开公开(公告)号：US20230326158A1
公开(公告)日：2023-10-12
申请号：US18149605
申请日：2023-01-03
Applicant: AUTODESK, INC.
Inventor： Hooman SHAYANI , Marco FUMERO , Aditya SANGHI
IPC: G06T19/20 , G06N3/0475 , G06N3/092
CPC classification number: G06T19/20 , G06N3/0475 , G06T2219/2024 , G06T2219/2021 , G06N3/092
Abstract: One embodiment of the present invention sets forth a technique for training a machine learning model to perform style transfer. The technique includes applying one or more augmentations to a first input three-dimensional (3D) shape to generate a second input 3D shape. The technique also includes generating, via a first set of neural network layers, a style code based on a first latent representation of the first input 3D shape and a second latent representation of the second input 3D shape. The technique further includes generating, via a second set of neural network layers, a first output 3D shape based on the style code and the second latent representation, and performing one or more operations on the first and second sets of neural network layers based on a first loss associated with the first output 3D shape to generate a trained machine learning model.
-
公开(公告)号：US20220156420A1
公开(公告)日：2022-05-19
申请号：US17523749
申请日：2021-11-10
Applicant: AUTODESK, INC.
Inventor： Peter MELTZER , Amir Hosein KHAS AHMADI , Pradeep Kumar JAYARAMAN , Joseph George LAMBOURNE , Aditya SANGHI , Hooman SHAYANI
Abstract: In various embodiments, a style comparison application generates visualization(s) of geometric style gradient(s). The style comparison application generates a first set of style signals based on a first 3D CAD object and generates a second set of style signals based on a second 3D CAD object. Based on the first and second sets of style signals, the style comparison application computes a different partial derivative of a style comparison metric for each position included in a set of positions associated with the first 3D CAD object to generate a geometric style gradient. The style comparison application generates a graphical element based on at least one of the direction or the magnitude of a vector in the geometric style gradient and positions the graphical element relative to a graphical representation of the first 3D CAD object within a graphical user interface to generate a visualization of the geometric style gradient.
-
Patent Agency Ranking
公开(公告)号：US20200050736A1
公开(公告)日：2020-02-13
申请号：US16534982
申请日：2019-08-07
Applicant: AUTODESK, INC.
Inventor： Hooman SHAYANI , Mark Thomas DAVIS
Abstract: In various embodiments, a stylization application generates designs that reflect stylistic preferences. In operation, the stylization application computes characterization information based on a first design and a trained machine-learning model that maps one or more designs to characterization information associated with one or more styles. The stylization application then computes a style score based on the characterization information and a target style that is included in the one or more styles. Subsequently, the stylization application generates a second design based on the style score, where the second design is more representative of the target style than the first design. Advantageously, because the stylization application can substantially increase the number of designs that can be generated based on the target style in a given amount of time, relative to more manual prior art techniques, the overall quality of the design ultimately selected for production can be improved.
-
公开(公告)号：US20220076488A1
公开(公告)日：2022-03-10
申请号：US17526877
申请日：2021-11-15
Applicant: AUTODESK, INC.
Inventor： Hooman SHAYANI , Mark Thomas DAVIS , Andriy BANADYHA , Stephen BARLEY
Abstract: In various embodiments, a stylization subsystem automatically modifies a three-dimensional (3D) object design. In operation, the stylization subsystem generates a simplified quad mesh based on an input triangle mesh that represents the 3D object design, a preferred orientation associated with at least a portion of the input triangle mesh, and mesh complexity constraint(s). The stylization subsystem then converts the simplified quad mesh to a simplified T-spline. Subsequently, the stylization subsystem creases one or more of edges included in the simplified T-spline to generate a stylized T-spline. Notably, the stylized T-spline represents a stylized design that is more convergent with the preferred orientation(s) than the 3D object design. Advantageously, relative to prior art approaches, the stylization subsystem can more efficiently modify the 3D object design to improve overall aesthetics and manufacturability.
-
公开(公告)号：US20200050710A1
公开(公告)日：2020-02-13
申请号：US16534985
申请日：2019-08-07
Applicant: AUTODESK, INC.
Inventor： Hooman SHAYANI , Mark Thomas DAVIS
Abstract: In various embodiments, a workflow application generates and evaluates designs that reflect stylistic preferences. In operation, the workflow application determines a target style based on input received via a graphical user interface (GUI). Notably, the target style characterizes a first set of designs. The workflow application then generates stylized design(s) based on stylization algorithm(s) associated with the target style. Subsequently, the workflow application, displays a subset of the stylized design(s) via the GUI. A stylized design included in the subset of stylized design(s) is ultimately selected for production via the GUI. Advantageously, because the workflow application can substantially increase the number of designs that can be generated and evaluated based on the target style in a given amount of time, relative to more manual prior art techniques, the overall quality of the stylized design selected for production can be improved.
-
公开(公告)号：US20170148207A1
公开(公告)日：2017-05-25
申请号：US15243706
申请日：2016-08-22
Applicant: AUTODESK, Inc.
Inventor： Xuejun SHENG , Hooman SHAYANI , Robert BOLTER
Abstract: In various embodiments of the present invention, a blending engine blends multiple surfaces included in a three-dimensional (3D) model of an object. First, the blending engine trims off portions of the surfaces that are targeted for blending at trimming curves to generate trimmed surfaces. The blending engine then constructs a single parametric blending surface via a unified parametrization for the trimming curves. Notably, to achieve the unified parametrization, the blending engine performs one or more spherical parametrization operations that generate parametrized curves based on the trimming curves and a fundamental sphere. After constructing the parametric blending surface based on the parametrized curves, the blending engine joins the parametric blending surface to the trimmed surfaces to produce a final, smooth intersection between the surfaces. Advantageously, because the blending engine creates a single parametric blending surface, the blending engine can blend arbitrary pipe surfaces and is compatible with computer-aided design modeling subsystems.
-
10.发明申请公开(公告)号：US20220318637A1
公开(公告)日：2022-10-06
申请号：US17348338
申请日：2021-06-15
Applicant: AUTODESK, INC.
Inventor： Pradeep Kumar JAYARAMAN , Thomas Ryan DAVIES , Joseph George LAMBOURNE , Nigel Jed Wesley MORRIS , Aditya SANGHI , Hooman SHAYANI
IPC: G06N3/08 , G06N3/04 , G06F30/10 , G06F16/901
Abstract: In various embodiments, an inference application performs tasks associated with 3D CAD objects that are represented using B-reps. A UV-net representation of a 3D CAD object that is represented using a B-rep includes a set of 2D UV-grids and a graph. In operation, the inference application maps the set of 2D UV-grids to a set of node feature vectors via a trained neural network. Based on the node feature vectors and the graph, the inference application computes a final result via a trained graph neural network. Advantageously, the UV-net representation of the 3D CAD object enabled the trained neural network and the trained graph neural network to efficiently process the 3D CAD object.
-
-
-
-
-
-
-
-
-
Search Results
17
records
(took 0.014 seconds)
